#include <stdio.h>
#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libavutil/avutil.h>
#include <libavutil/opt.h>
#include <libswresample/swresample.h>
#include <libswscale/swscale.h>
#include <libavutil/timestamp.h>
#define STREAM_DURATION 50.0
#define STREAM_FRAME_RATE 25 /* 25 images/s */
#define STREAM_PIX_FMT AV_PIX_FMT_YUV420P /* default pix_fmt */
#define SCALE_FLAGS SWS_BICUBIC
// a wrapper around a single output AVStream
typedef struct OutputStream {
AVStream *st;
AVCodecContext *enc;
/* pts of the next frame that will be generated */
int64_t next_pts;
int samples_count;
AVFrame *frame;
AVFrame *tmp_frame;
float t, tincr, tincr2;
struct SwsContext *sws_ctx;
struct SwrContext *swr_ctx;
} OutputStream;
static AVFrame *alloc_audio_frame(enum AVSampleFormat sample_fmt,
uint64_t channel_layout,
int sample_rate, int nb_samples)
{
AVFrame *frame = av_frame_alloc();
int ret;
if (!frame) {
fprintf(stderr, "Error allocating an audio frame\n");
exit(1);
}
frame->format = sample_fmt;
frame->channel_layout = channel_layout;
frame->sample_rate = sample_rate;
frame->nb_samples = nb_samples;
if (nb_samples) {
ret = av_frame_get_buffer(frame, 0);
if (ret < 0) {
fprintf(stderr, "Error allocating an audio buffer\n");
exit(1);
}
}
return frame;
}
static AVFrame *alloc_picture(enum AVPixelFormat pix_fmt, int width, int height)
{
AVFrame *picture;
int ret;
picture = av_frame_alloc();
if (!picture)
return NULL;
picture->format = pix_fmt;
picture->width = width;
picture->height = height;
/* allocate the buffers for the frame data */
ret = av_frame_get_buffer(picture, 32);
if (ret < 0) {
fprintf(stderr, "Could not allocate frame data.\n");
exit(1);
}
return picture;
}
static void log_packet(const AVFormatContext *fmt_ctx, const AVPacket *pkt)
{
AVRational *time_base = &fmt_ctx->streams[pkt->stream_index]->time_base;
printf("pts:%s pts_time:%s dts:%s dts_time:%s duration:%s duration_time:%s stream_index:%d\n",
av_ts2str(pkt->pts), av_ts2timestr(pkt->pts, time_base),
av_ts2str(pkt->dts), av_ts2timestr(pkt->dts, time_base),
av_ts2str(pkt->duration), av_ts2timestr(pkt->duration, time_base),
pkt->stream_index);
}
static int write_frame(AVFormatContext *fmt_ctx, const AVRational *time_base, AVStream *st, AVPacket *pkt)
{
/* rescale output packet timestamp values from codec to stream timebase */
av_packet_rescale_ts(pkt, *time_base, st->time_base);
pkt->stream_index = st->index;
/* Write the compressed frame to the media file. */
log_packet(fmt_ctx, pkt);
return av_interleaved_write_frame(fmt_ctx, pkt);
}
/* Prepare a 16 bit dummy audio frame of 'frame_size' samples and
* 'nb_channels' channels. */
static AVFrame *get_audio_frame(OutputStream *ost)
{
AVFrame *frame = ost->tmp_frame;
int j, i, v;
int16_t *q = (int16_t*)frame->data[0];
/* check if we want to generate more frames */
if (av_compare_ts(ost->next_pts, ost->enc->time_base,
STREAM_DURATION, (AVRational){ 1, 1 }) >= 0)
return NULL;
for (j = 0; j <frame->nb_samples; j++) {
v = (int)(sin(ost->t) * 10000);
for (i = 0; i < ost->enc->channels; i++)
*q++ = v;
ost->t += ost->tincr;
ost->tincr += ost->tincr2;
}
frame->pts = ost->next_pts;
ost->next_pts += frame->nb_samples;
return frame;
}
/*
* encode one audio frame and send it to the muxer
* return 1 when encoding is finished, 0 otherwise
*/
static int write_audio_frame(AVFormatContext *oc, OutputStream *ost)
{
AVCodecContext *c;
AVPacket pkt = { 0 }; // data and size must be 0;
AVFrame *frame;
int ret;
int got_packet;
int dst_nb_samples;
av_init_packet(&pkt);
c = ost->enc;
frame = get_audio_frame(ost);
if (frame) {
/* convert samples from native format to destination codec format, using the resampler */
/* compute destination number of samples */
dst_nb_samples = av_rescale_rnd(swr_get_delay(ost->swr_ctx, c->sample_rate) + frame->nb_samples,
c->sample_rate, c->sample_rate, AV_ROUND_UP);
//av_assert0(dst_nb_samples == frame->nb_samples);
/* when we pass a frame to the encoder, it may keep a reference to it
* internally;
* make sure we do not overwrite it here
*/
ret = av_frame_make_writable(ost->frame);
if (ret < 0){
exit(1);
}
/* convert to destination format */
ret = swr_convert(ost->swr_ctx,
ost->frame->data, dst_nb_samples,
(const uint8_t **)frame->data, frame->nb_samples);
if (ret < 0) {
fprintf(stderr, "Error while converting\n");
exit(1);
}
frame = ost->frame;
frame->pts = av_rescale_q(ost->samples_count, (AVRational){1, c->sample_rate}, c->time_base);
ost->samples_count += dst_nb_samples;
}
ret = avcodec_encode_audio2(c, &pkt, frame, &got_packet);
if (ret < 0) {
fprintf(stderr, "Error encoding audio frame: %s\n", av_err2str(ret));
exit(1);
}
if (got_packet) {
ret = write_frame(oc, &c->time_base, ost->st, &pkt);
if (ret < 0) {
fprintf(stderr, "Error while writing audio frame: %s\n",
av_err2str(ret));
exit(1);
}
}
return (frame || got_packet) ? 0 : 1;
}
/* Prepare a dummy image. */
static void fill_yuv_image(AVFrame *pict, int frame_index,
int width, int height)
{
int x, y, i;
i = frame_index;
/* Y */
for (y = 0; y < height; y++)
for (x = 0; x < width; x++)
pict->data[0][y * pict->linesize[0] + x] = x + y + i * 3;
/* Cb and Cr */
for (y = 0; y < height / 2; y++) {
for (x = 0; x < width / 2; x++) {
pict->data[1][y * pict->linesize[1] + x] = 128 + y + i * 2;
pict->data[2][y * pict->linesize[2] + x] = 64 + x + i * 5;
}
}
}
static AVFrame *get_video_frame(OutputStream *ost)
{
AVCodecContext *c = ost->enc;
/* check if we want to generate more frames */
if (av_compare_ts(ost->next_pts, c->time_base,
STREAM_DURATION, (AVRational){ 1, 1 }) >= 0)
return NULL;
/* when we pass a frame to the encoder, it may keep a reference to it
* internally; make sure we do not overwrite it here */
if (av_frame_make_writable(ost->frame) < 0)
exit(1);
if (ost->sws_ctx) {
/* as we only generate a YUV420P picture, we must convert it
* to the codec pixel format if needed */
fill_yuv_image(ost->tmp_frame, ost->next_pts, c->width, c->height);
sws_scale(ost->sws_ctx, (const uint8_t * const *) ost->tmp_frame->data,
ost->tmp_frame->linesize, 0, c->height, ost->frame->data,
ost->frame->linesize);
} else {
fill_yuv_image(ost->frame, ost->next_pts, c->width, c->height);
}
ost->frame->pts = ost->next_pts++;
return ost->frame;
}
/*
* encode one video frame and send it to the muxer
* return 1 when encoding is finished, 0 otherwise
*/
static int write_video_frame(AVFormatContext *oc, OutputStream *ost)
{
int ret;
AVCodecContext *c;
AVFrame *frame;
int got_packet = 0;
AVPacket pkt = { 0 };
c = ost->enc;
frame = get_video_frame(ost);
av_init_packet(&pkt);
/* encode the image */
ret = avcodec_encode_video2(c, &pkt, frame, &got_packet);
if (ret < 0) {
fprintf(stderr, "Error encoding video frame: %s\n", av_err2str(ret));
exit(1);
}
printf("-----get video frame2 %p %d %p %d %p\n",frame,got_packet,c,pkt.size,ost->st);
if (got_packet) {
ret = write_frame(oc, &c->time_base, ost->st, &pkt);
} else {
ret = 0;
}
if (ret < 0) {
fprintf(stderr, "Error while writing video frame: %s\n", av_err2str(ret));
exit(1);
}
return (frame || got_packet) ? 0 : 1;
}
int main(int argc,char** argv)
{
char* filename = "test.mp4";
AVFormatContext *oc = NULL;
int ret = avformat_alloc_output_context2(&oc,NULL,NULL,filename);
if(ret !=0 ){
printf("avformat alloc output context2 failed\n");
return 0;
}
AVOutputFormat* fmt = oc->oformat;
printf("fmt->video_codec %d\n",fmt->video_codec);
printf("fmt->audio_codec %d\n",fmt->audio_codec);
OutputStream audio_st = {0};
OutputStream video_st = {0};
int encode_audio = 0;
int encode_video = 0;
if( fmt->audio_codec != AV_CODEC_ID_NONE )
{
AVCodec* codec = avcodec_find_encoder(fmt->audio_codec);
if(codec == NULL){
printf("can not find codec\n");
return 0;
}
AVCodecContext * c = avcodec_alloc_context3(codec);
if(c == NULL){
printf("can not alloc context \n");
return 0;
}
AVStream* st = avformat_new_stream(oc,NULL);
if(st == NULL){
printf("cant not alloc st \n");
return 0;
}
c->sample_fmt = codec->sample_fmts? codec->sample_fmts[0]:AV_SAMPLE_FMT_FLTP;
c->bit_rate = 64000;
c->sample_rate = 44100;
if(codec->supported_samplerates){
c->sample_rate = codec->supported_samplerates[0];
for(int i = 0; codec->supported_samplerates[i];i++){
if(codec->supported_samplerates[i]==44100){
c->sample_rate = 44100;
}
}
}
c->channel_layout = AV_CH_LAYOUT_STEREO;
if(codec->channel_layouts){
c->channel_layout = codec->channel_layouts[0];
for(int i = 0;codec->channel_layouts[i];i++){
if(codec->channel_layouts[i]==AV_CH_LAYOUT_STEREO){
c->channel_layout = AV_CH_LAYOUT_STEREO;
}
}
}
c->channels = av_get_channel_layout_nb_channels(c->channel_layout);
if (oc->oformat->flags & AVFMT_GLOBALHEADER)
c->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
int ret = avcodec_open2(c, codec, NULL);
if(ret < 0){
printf("avcodec_open2 failed\n");
return 0;
}
//设置ST的信息
st->id = oc->nb_streams-1;
st->time_base = (AVRational){1,c->sample_rate};
ret = avcodec_parameters_from_context(st->codecpar, c);
if (ret < 0) {
fprintf(stderr, "Could not copy the stream parameters\n");
return 0;
}
//申请空间
int nb_samples;
if (c->codec->capabilities & AV_CODEC_CAP_VARIABLE_FRAME_SIZE)
nb_samples = 10000;
else
nb_samples = c->frame_size;
AVFrame* frame = alloc_audio_frame(c->sample_fmt,c->channel_layout,c->sample_rate,nb_samples);
AVFrame* tmp_frame = alloc_audio_frame(AV_SAMPLE_FMT_S16,c->channel_layout,c->sample_rate,nb_samples);
//申请重采样的参数
SwrContext * swr_ctx = swr_alloc();
if(swr_ctx==NULL){
printf("swr_ctx alloc failed\n");
return 0;
}
/* set options */
av_opt_set_int (swr_ctx, "in_channel_count", c->channels, 0);
av_opt_set_int (swr_ctx, "in_sample_rate", c->sample_rate, 0);
av_opt_set_sample_fmt(swr_ctx, "in_sample_fmt", AV_SAMPLE_FMT_S16, 0);
av_opt_set_int (swr_ctx, "out_channel_count", c->channels, 0);
av_opt_set_int (swr_ctx, "out_sample_rate", c->sample_rate, 0);
av_opt_set_sample_fmt(swr_ctx, "out_sample_fmt", c->sample_fmt, 0);
/* initialize the resampling context */
if ((ret = swr_init(swr_ctx)) < 0) {
fprintf(stderr, "Failed to initialize the resampling context\n");
exit(1);
}
//设置输出流的信息
audio_st.st = st;
audio_st.enc = c;
audio_st.frame = frame;
audio_st.tmp_frame = tmp_frame;
audio_st.swr_ctx = swr_ctx;
audio_st.t = 0;
audio_st.tincr = 2 * M_PI * 110.0 / c->sample_rate;
audio_st.tincr2 = 2 * M_PI * 110.0 / c->sample_rate / c->sample_rate;
encode_audio = 1;
}
if( fmt->video_codec != AV_CODEC_ID_NONE )
{
AVCodec* codec = avcodec_find_encoder(fmt->video_codec);
if(codec == NULL){
printf("can not find codec\n");
return 0;
}
AVCodecContext * c = avcodec_alloc_context3(codec);
if(c == NULL){
printf("can not alloc context \n");
return 0;
}
AVStream* st = avformat_new_stream(oc,NULL);
if(st == NULL){
printf("cant not alloc st \n");
return 0;
}
c->bit_rate = 400000;
c->width = 352;
c->height = 288;
c->codec_id = fmt->video_codec;
c->time_base = (AVRational){1,STREAM_FRAME_RATE};
c->gop_size = 12;
c->pix_fmt = STREAM_PIX_FMT;
if(c->codec_id == AV_CODEC_ID_MPEG2VIDEO){
c->max_b_frames = 2;
}
if(c->codec_id == AV_CODEC_ID_MPEG1VIDEO){
c->mb_decision = 2;
}
/* Some formats want stream headers to be separate. */
if (oc->oformat->flags & AVFMT_GLOBALHEADER)
c->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
int ret = avcodec_open2(c, codec, NULL);
if(ret < 0){
printf("avcodec_open2 failed\n");
return 0;
}
//设置st的参数
st->time_base = c->time_base;
st->id = oc->nb_streams-1;
ret = avcodec_parameters_from_context(st->codecpar, c);
if (ret < 0) {
fprintf(stderr, "Could not copy the stream parameters\n");
return 0;
}
//申请空间
/* allocate and init a re-usable frame */
AVFrame* frame = alloc_picture(c->pix_fmt, c->width, c->height);
if (!frame) {
fprintf(stderr, "Could not allocate video frame\n");
exit(1);
}
/* If the output format is not YUV420P, then a temporary YUV420P
* picture is needed too. It is then converted to the required
* output format. */
AVFrame* tmp_frame = NULL;
if (c->pix_fmt != AV_PIX_FMT_YUV420P) {
tmp_frame = alloc_picture(AV_PIX_FMT_YUV420P, c->width, c->height);
if (!tmp_frame) {
fprintf(stderr, "Could not allocate temporary picture\n");
exit(1);
}
}
//初始化色彩空间转换
struct SwsContext* sws_ctx = NULL;
if(tmp_frame!=NULL){
sws_ctx = sws_getContext(c->width, c->height,
AV_PIX_FMT_YUV420P,
c->width, c->height,
c->pix_fmt,
SCALE_FLAGS, NULL, NULL, NULL);
if (sws_ctx) {
fprintf(stderr,
"Could not initialize the conversion context\n");
exit(1);
}
}
//设置输出的流的信息
video_st.st = st;
video_st.enc = c;
video_st.sws_ctx = sws_ctx;
video_st.frame = frame;
video_st.tmp_frame = tmp_frame;
printf("st=%p enc = %p sws_ctx=%p frame=%p tmp_frame=%p\n",st,c,sws_ctx,frame,tmp_frame);
encode_video = 1;
}
av_dump_format(oc, 0, filename, 1);
ret = avio_open(&oc->pb,filename,AVIO_FLAG_WRITE);
if(ret < 0){
printf("avio open failed\n");
exit(1);
}
ret = avformat_write_header(oc,NULL);
if(ret < 0){
printf("avformat_write_header failed\n");
exit(1);
}
while(encode_audio || encode_video ){
if (encode_video &&
(!encode_audio || av_compare_ts(video_st.next_pts, video_st.enc->time_base,
audio_st.next_pts, audio_st.enc->time_base) <= 0)) {
encode_video = !write_video_frame(oc, &video_st);
} else {
encode_audio = !write_audio_frame(oc, &audio_st);
}
}
av_write_trailer(oc);
avformat_free_context(oc);
printf("write succeed\n");
return 0;
}